© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 59233
    Prev
    Next
    INDEX
    Explanations

    references to SMS and related messaging technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UNET
    -0.08
    exus
    -0.07
    hq
    -0.07
    elling
    -0.07
    keh
    -0.07
    ت
    -0.07
    JsonValue
    -0.07
    ESCO
    -0.07
    anager
    -0.07
    umbled
    -0.07
    POSITIVE LOGITS
     latter
    0.08
    ahan
    0.07
    ÄĽÅĻ
    0.07
    verity
    0.07
    gart
    0.06
    ï¸
    0.06
    ieux
    0.06
    esModule
    0.06
    .SetActive
    0.06
    ÙĨدا
    0.06
    Activations Density 0.007%

    No Known Activations